INDEX

Explanations

references to technical specifications or details in a context, especially relating to computing or scientific descriptions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

脚注の使い方

-0.76

 Wicidata

-0.55

expandindo

-0.55

 numerus

-0.55

 lenker

-0.53

vaadin

-0.51

stateProvider

-0.50

scrapy

-0.50

 الحره

-0.49

 Unwin

-0.49

POSITIVE LOGITS

IntoConstraints

0.66

 ProtoMessage

0.60

 transfieras

0.57

jsxFileName

0.56

évaluateur

0.56

Билгалдахарш

0.55

zaamheid

0.53

цездатний

0.53

новништво

0.53

JvmStatic

0.51

Activations Density 1.319%

references to technical specifications or details in a context, especially relating to computing or scientific descriptions

No Comments

No Known Activations